Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to political parties or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.03
    2:0.09
    3:0.23
    4:0.04
    5:0.03
    6:0.16
    7:0.09
    8:0.04
    9:0.05
    10:0.08
    11:0.05
    Negative Logits
     ingred
    -1.17
     Prosecut
    -1.16
    NetMessage
    -1.12
     cher
    -1.09
    Parent
    -1.06
    amen
    -1.05
     sugg
    -1.04
    ��
    -1.02
    rily
    -1.01
    utory
    -1.01
    POSITIVE LOGITS
    iform
    1.06
    Plex
    1.05
    alore
    1.04
    pite
    0.99
    ascript
    0.95
    akery
    0.95
    ordan
    0.94
    DragonMagazine
    0.94
    elt
    0.94
    hyde
    0.94
    Act Density 0.004%

    No Known Activations